{"id":20779429,"url":"https://github.com/freedomintelligence/textclassificationbenchmark","last_synced_at":"2025-04-13T00:49:16.987Z","repository":{"id":77765322,"uuid":"114098658","full_name":"FreedomIntelligence/TextClassificationBenchmark","owner":"FreedomIntelligence","description":"A Benchmark of Text Classification in PyTorch","archived":false,"fork":false,"pushed_at":"2024-04-20T01:36:55.000Z","size":1841,"stargazers_count":603,"open_issues_count":21,"forks_count":137,"subscribers_count":32,"default_branch":"master","last_synced_at":"2025-04-13T00:49:13.192Z","etag":null,"topics":["attention-is-all-you-need","benchmark","capusle","cnn","cnn-classification","crnn","lstm","lstm-sentiment-analysis","pytorch","quantum","rcnn","text-classification"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/FreedomIntelligence.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2017-12-13T09:08:33.000Z","updated_at":"2025-03-24T07:14:27.000Z","dependencies_parsed_at":"2024-11-24T15:15:15.458Z","dependency_job_id":null,"html_url":"https://github.com/FreedomIntelligence/TextClassificationBenchmark","commit_stats":null,"previous_names":["wabyking/textclassificationbenchmark"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreedomIntelligence%2FTextClassificationBenchmark","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreedomIntelligence%2FTextClassificationBenchmark/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreedomIntelligence%2FTextClassificationBenchmark/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreedomIntelligence%2FTextClassificationBenchmark/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/FreedomIntelligence","download_url":"https://codeload.github.com/FreedomIntelligence/TextClassificationBenchmark/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248650436,"owners_count":21139672,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["attention-is-all-you-need","benchmark","capusle","cnn","cnn-classification","crnn","lstm","lstm-sentiment-analysis","pytorch","quantum","rcnn","text-classification"],"created_at":"2024-11-17T13:27:53.586Z","updated_at":"2025-04-13T00:49:16.969Z","avatar_url":"https://github.com/FreedomIntelligence.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Text Classification Benchmark\nA Benchmark of Text Classification in PyTorch\n\n\n## Motivation\n\nWe are trying to build a Benchmark for Text Classification including\n\n\n\u003eMany Text Classification  **DataSet**, including Sentiment/Topic Classfication, popular language(e.g. English and Chinese). Meanwhile, a basic word embedding is provided.\n\n\u003eImplment many popular and state-of-art **Models**, especially in deep neural network.\n\n## Have done\nWe have done some dataset and models\n### Dataset done\n- IMDB\n- SST \n- Trec\n\n### Models done\n- FastText\n- BasicCNN (KimCNN,MultiLayerCNN, Multi-perspective CNN)\n- InceptionCNN\n- LSTM (BILSTM, StackLSTM)\n- LSTM with Attention (Self Attention / Quantum Attention)\n- Hybrids between CNN and RNN (RCNN, C-LSTM)\n- Transformer - Attention is all you need\n- ConS2S\n- Capsule\n- Quantum-inspired NN\n\n## Libary\n\nYou should have install [these librarys](docs/windows_torch_en.md)\n\u003cpre\u003e\npython3\ntorch\ntorchtext (optional)\n\u003c/pre\u003e\n\n## Dataset \nDataset will be automatically configured in current path, or download manually your data in [Dataset](docs/data_config_en.md),  step-by step.\n\nincluding\n\u003cpre\u003e\nGlove embeding\nSentiment classfication dataset IMDB\n\u003c/pre\u003e\n\n\n## usage\n\n\nRun in default  setting\n\u003cpre\u003e\u003ccode\u003epython main.py\u003c/code\u003e\u003c/pre\u003e\n\nCNN \n\u003cpre\u003e\u003ccode\u003epython main.py --model cnn\u003c/code\u003e\u003c/pre\u003e\n\nLSTM\n\u003cpre\u003e\u003ccode\u003epython main.py --model lstm\u003c/code\u003e\u003c/pre\u003e\n\n## Road Map\n- [X] Data preprossing framework\n- [X] Models modules\n- [ ] Loss, Estimator and hyper-paramter tuning.\n- [ ] Test modules\n- [ ] More Dataset\n- [ ] More models\n\n\n\n## Organisation of the repository\nThe core of this repository is models and dataset.\n\n\n* ```dataloader/```: loading all dataset such as ```IMDB```, ```SST```\n\n* ```models/```: creating all models such as ```FastText```, ```LSTM```,```CNN```,```Capsule```,```QuantumCNN``` ,```Multi-Head Attention```\n\n* ```opts.py```: Parameter and config info.\n\n* ```utils.py```: tools.\n\n* ```dataHelper```: data helper\n\n\n\n\n## Contributor\n-\t[@Allenzhai](https://github.com/zhaizheng)\n-\t[@JaredWei](https://github.com/jacobwei)\n-\t[@AlexMeng](https://github.com/EdwardLorenz)\n-\t[@Lilianwang](https://github.com/WangLilian)\n-\t[@ZhanSu](https://github.com/shuishen112)\n-\t[@Wabywang](https://github.com/Wabyking)\n\nWelcome your issues and contribution!!!\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffreedomintelligence%2Ftextclassificationbenchmark","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffreedomintelligence%2Ftextclassificationbenchmark","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffreedomintelligence%2Ftextclassificationbenchmark/lists"}